Table 2.

The suggested network architecture’s ideal parameters were chosen.

Parameters	Values	Optimal Value
Batch Size in GAN	4, 6, 8, 10, 12	10
Optimizer in GAN	Adam, SGD, Adamax	SGD
Number of CNN Layers	3, 4, 5	4
Learning Rate in GAN	0.1, 0.01, 0.001, 0.0001	0.0001
Number of Graph Conv Layers	2, 3, 4, 5, 6, 7	6
Batch Size in GCN	8, 16, 32	16
Batch normalization	ReLU, Leaky-ReLU, TF-2	TF-2
Learning Rate in GCN	0.1, 0.01, 0.001, 0.0001, 0.00001	0.001
Dropout Rate	0.1, 0.2, 0.3	0.1
Weight of optimizer	$4\times {10}^{-3},4\times {10}^{-4},4\times {10}^{-5},4\times {10}^{-6},4\times {10}^{-7}$	$4\times {10}^{-6}$
Error function	MSE, Cross Entropy	Cross Entropy
Optimizer in GCN	Adam, SGD, Adadelta, Adamax	Adadelta